INDEX

Explanations

mathematical symbols and expressions, particularly those related to functions and variables in equations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 بيها

-0.53

</em>

-0.53

 consider

-0.52

';

-0.51

-0.50

Lu

-0.50

 scale

-0.50

</i>

-0.47

 Meksiku

-0.47

alou

-0.47

POSITIVE LOGITS

存于互联网档案馆

0.74

✨:

0.69

setVerticalGroup

0.68

TagMode

0.68

RegressionTest

0.68

styleUrls

0.68

Eſ

0.66

ReusableCell

0.65

esModule

0.65

tanleria

0.64

Activations Density 2.935%

mathematical symbols and expressions, particularly those related to functions and variables in equations

No Comments

No Known Activations